Qwen3 Coder 30B A3B Instruct
AlibabaQwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
In
$0.07
Out
$0.28
Blended
$0.12
Where to buy this model
4 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| $0.07 | $0.27 | $0.12 | - | |
| ● SiliconFlow fp8 | $0.07 | $0.28 | $0.12 | +0% |
 Amazon Bedrock | $0.15 | $0.60 | $0.26 | +117% |
| ● Alibaba | $0.29 | $1.46 | $0.59 | +392% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 262K
- max output
- 236K
- Family
- qwen
- Modalities
- text
- Features
- json · tools
Live pricing, updated 2026-09-15.